Differentially Private Auditing Under Strategic Response

• URL: http://arxiv.org/abs/2605.07674v1
• Date: Fri, 08 May 2026 12:44:03 GMT
• Title: Differentially Private Auditing Under Strategic Response
• Abstract summary: We study audit design when the audited developer can strategically respond to the privacy-constrained audit interface.<n>We formalize privacy-constrained auditing as a bilevel Stackelberg game, in which an auditor commits to a query policy and DP budget allocation across harm dimensions.<n>We propose Strategic Private Audit Design (SPAD), a projected-gradient algorithm with hypergradients computed through the developer's best response.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Regulatory audits of AI systems increasingly rely on differential privacy (DP) to protect training data and model internals. We study audit design when the audited developer can strategically respond to the privacy-constrained audit interface. We formalize privacy-constrained auditing as a bilevel Stackelberg game, in which an auditor commits to a query policy and DP budget allocation across harm dimensions, and a strategic developer reallocates mitigation efforts in response. We introduce the welfare-weighted under-detection gap $B_w$, the welfare-weighted true residual harm the audit fails to detect at the developer's strategic best response, and prove that naive DP auditing (uniform or harm-proportional allocation) induces a strictly larger $B_w$ than any non-strategic mitigation baseline whenever effective detectability is heterogeneous, the welfare weights are not comonotone with detectability, and the developer's optimum is interior. We characterize the optimal auditor allocation as a four-factor balance of welfare weight, audit miss-probability, detectability elasticity, and mitigation-cost curvature, and provide a single-level reformulation of the bilevel problem via the developer's KKT system. We propose Strategic Private Audit Design (SPAD), a projected-gradient algorithm with hypergradients computed through the developer's best response.

Related papers

• Fairness Auditing: Lower Bounds on Company Manipulation [4.867679624126028]
  Fairness audits are increasingly mandated in high-stakes applications such as hiring, lending, and automated decision-making.<n>Recent work has established fundamental impossibility results for black-box fairness auditing.<n>We quantify the extent of unavoidable post-audit manipulation under finite audit resources.
  arXiv  Detail & Related papers  (2026-08-01T10:11:20Z)
• SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute [62.3458279176813]
  Self-Verifying Refinement is an oracle-free multi-turn reinforcement learning framework.<n>It learns to use self-verification as a compute-control policy.<n>It achieves a macro-average accuracy of 0.563 with only 2.99 inference turns on average.
  arXiv  Detail & Related papers  (2026-07-30T16:20:58Z)
• Optimal Guarantees for Auditing Rényi Differentially Private Machine Learning [15.701798841393668]
  We study black-box auditing for machine learning algorithms that claim R 'enyi differential privacy (RDP) guarantees.<n>We introduce an auditing framework, based on hypothesis testing, that directly estimates Rényi divergence between neighboring executions using the Donsker-Varadhan (DV) variational estimator.<n>Our analysis yields explicit and non-asymptotic confidence intervals for auditing via class-restricted DV estimators, separating statistical estimation error from algorithmic privacy leakage.
  arXiv  Detail & Related papers  (2026-05-21T03:18:09Z)
• A Benchmark for Strategic Auditee Gaming Under Continuous Compliance Monitoring [1.253312107729806]
  Continuous post-deployment compliance audits create a class of strategic gaming.<n>We formalize continuous auditing as a $T$-round Stackelberg game between an auditor that commits to a temporal policy and an adaptive auditee.
  arXiv  Detail & Related papers  (2026-05-07T14:28:34Z)
• Automated Self-Testing as a Quality Gate: Evidence-Driven Release Management for LLM Applications [51.56484100374058]
  We present an automated self-testing framework that introduces quality gates with evidence-based release decisions.<n>We evaluate the framework through a longitudinal case study of an internally deployed multi-agent conversational AI system.
  arXiv  Detail & Related papers  (2026-03-13T20:44:15Z)
• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• Governing AI Forgetting: Auditing for Machine Unlearning Compliance [30.173215964349044]
  We introduce the first economic framework for auditing machine unlearning compliance, by integrating certified unlearning theory with regulatory enforcement.<n>We first characterize MU's inherent verification uncertainty using a hypothesis-testing interpretation of certified unlearning.<n>We then propose a game-theoretic model to capture the strategic interactions between the auditor and the operator.
  arXiv  Detail & Related papers  (2026-02-16T08:32:09Z)
• Making LLMs Reliable When It Matters Most: A Five-Layer Architecture for High-Stakes Decisions [51.56484100374058]
  Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes.<n>This gap, driven by mutually cognitive biases in both humans and artificial intelligence (AI) systems, threatens the defensibility of valuations and sustainability of investments in the sector.<n>This report describes a framework emerging from systematic qualitative assessment across 7 frontier-grade LLMs and 3 market-facing venture vignettes under time pressure.
  arXiv  Detail & Related papers  (2025-11-10T22:24:21Z)
• Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking [78.69179041551014]
  We propose an information-theoretic reward modeling framework based on the Information Bottleneck principle.<n>We show that InfoRM filters out preference-irrelevant information to alleviate reward misgeneralization.<n>We also introduce IBL, a distribution-level regularization that penalizes such deviations, effectively expanding the optimization landscape.
  arXiv  Detail & Related papers  (2025-10-15T15:51:59Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• A Game-Theoretic Analysis of Auditing Differentially Private Algorithms with Epistemically Disparate Herd [16.10098472773814]
  This study examines the impact of herd audits on algorithm developers using the Stackelberg game approach. By enhancing transparency and accountability, herd audit contributes to the responsible development of privacy-preserving algorithms.
  arXiv  Detail & Related papers  (2024-04-24T20:34:27Z)
• A fully decentralized auditing approach for edge computing: A Game-Theoretic Perspective [18.20120097647291]
  Edge storage presents a viable data storage alternative for application vendors. Data cached in edge computing systems is susceptible to intentional or accidental disturbances. This paper proposes a decentralized integrity auditing scheme to safeguard data integrity.
  arXiv  Detail & Related papers  (2023-12-26T11:26:44Z)
• TrustFed: A Reliable Federated Learning Framework with Malicious-Attack Resistance [8.924352407824566]
  Federated learning (FL) enables collaborative learning among multiple clients while ensuring individual data privacy. In this paper, we propose a hierarchical audit-based FL (HiAudit-FL) framework to enhance the reliability and security of the learning process. Our simulation results demonstrate that HiAudit-FL can effectively identify and handle potential malicious users accurately, with small system overhead.
  arXiv  Detail & Related papers  (2023-12-06T13:56:45Z)
• Algorithmic Fairness and Vertical Equity: Income Fairness with IRS Tax Audit Models [73.24381010980606]
  This study examines issues of algorithmic fairness in the context of systems that inform tax audit selection by the IRS. We show how the use of more flexible machine learning methods for selecting audits may affect vertical equity. Our results have implications for the design of algorithmic tools across the public sector.
  arXiv  Detail & Related papers  (2022-06-20T16:27:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.